A Novel Approach of Label Construction for Predicting Remaining Useful Life of Machinery

Rolling bearings are key components of rotating machinery, and predicting the remaining useful life (RUL) is of great significance in practical industrial scenarios and is being increasingly studied. A precise and reliable remaining useful life prediction result provides valuable information for decision-makers, which is essential to ensure the safety and reliability of mechanical systems. Generally, the RUL label is considered to be an ideal life curve, which is the benchmark for RUL prediction. However, the existing label construction methods make more use of expert experience and seldom mine knowledge from data and combine experience to assist in constructing a health index (HI). In this paper, a novel and simple approach of label construction is proposed for predicting the RUL accurately. More specifically, the degradation index of the multiscale frequency domain is first extracted. Furthermore, the fuzzy C-means (FCM) algorithm is innovatively used to divide the degradation data into several stages to obtain the turning point of degradation. Then, a nonlinear degradation index, the RUL label with the turning point, was constructed based on principal component analysis (PCA). Finally, the recurrent neural network (RNN) is used for prediction and verification. In order to verify the effectiveness of the proposed approach, two different bearing lifecycle datasets are gathered and analyzed. The analysis result confirms that the proposed method is able to achieve a better performance, which outperforms some existing methods.

Reliability Evaluation of CNC Machine Tools Considering Competing Failures of Fault Failure Data and Machining Accuracy Degradation Data

Traditional reliability evaluation of CNC machine tools usually considers a single failure mode of fault failure or degradation failure, or considers fault failure and degradation failure to be independent of each other. However, in the actual working conditions, fault failure and degradation failure are mutually affected, and the reliability evaluation of the competing failure models of CNC machine tools by considering the two failure modes comprehensively can get more accurate evaluation results. Therefore, this paper proposes a reliability evaluation method for CNC machine tools considering fault failure data competing with machining accuracy degradation data. A fault failure model of CNC machine tools is established based on a non-homogeneous Poisson process. The fault failure model is updated according to the different effects of each maintenance result of the failure on machining accuracy. By integrating multiple geometric errors of CNC machine tools through multi-body system theory, the amount of machining accuracy degradation is extracted. A machining accuracy degradation failure model is established using the Wiener process. Considering the correlation between fault failure and degradation failure, a competing failure model based on the Coupla function is developed for evaluating the reliability of CNC machine tools. Finally, the effectiveness of the proposed method is verified by example analysis.

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

Remaining useful life prediction with insufficient degradation data based on deep learning approach

Remaining useful life (RUL) prediction plays a crucial role in decision-making in conditionbased maintenance for preventing catastrophic field failure. For degradation-failed products, the data of performance deterioration process are the key for lifetime estimation. Deep learning has been proved to have excellent performance in RUL prediction given that the degradation data are sufficiently large. However, in some applications, the degradation data are insufficient, under which how to improve the prediction accuracy is yet a challenging problem. To tackle such a challenge, we propose a novel deep learning-based RUL prediction framework by amplifying the degradation dataset. Specifically, we leverage the cycle-consistent generative adversarial network to generate the synthetic data, based on which the original degradation dataset is amplified so that the data characteristics hidden in the sample space could be captured. Moreover, the sliding time window strategy and deep bidirectional long short-term memory network are employed to complete the RUL prediction framework. We show the effectiveness of the proposed method by running it on the turbine engine data set from the National Aeronautics and Space Administration. The comparative experiments show that our method outperforms a case without the use of the synthetically generated data.